Interpretable machine learning prediction of live birth after freeze-all FET cycles across transfer-order subgroups - Scorecard - MDSpire

Interpretable machine learning prediction of live birth after freeze-all FET cycles across transfer-order subgroups

  • By

  • Yu Zhao

  • He Wang

  • Lin Wang

  • Lei Yan

  • Jiao Liu

  • Mengyi Teng

  • Hao Wang

  • Ting Liu

  • July 17, 2026

Share

Clinical Scorecard: Predictive Modeling of Live Birth Outcomes Following Freeze-All FET Cycles: Insights from Transfer-Order Subgroup Analysis Using Interpretable Machine Learning Techniques

At a Glance

CategoryDetail
ConditionInfertility and Assisted Reproductive Technology
Key MechanismsTransfer-order heterogeneity affects live-birth prediction after freeze-all FET cycles.
Target PopulationIndividuals undergoing freeze-all FET cycles.
Care SettingReproductive Medicine Center

Key Highlights

  • Transfer-order subgroup modeling improves prediction accuracy.
  • CatBoost models showed AUCs of 0.704 for overall cohort and 0.812 for first-transfer subgroup.
  • Key predictors include female age, ovarian-reserve indicators, and basal progesterone.

Guideline-Based Recommendations

Diagnosis

  • Utilize transfer-order stratification for live-birth prediction.

Management

  • Implement machine learning models for pre-transfer counseling.

Monitoring & Follow-up

  • Assess model performance using ROC-derived Youden thresholds.

Risks

  • Consider the impact of transfer order on treatment expectations and outcomes.

Patient & Prescribing Data

Patients undergoing freeze-all FET cycles at a single center.

Predictive modeling can enhance individualized decision-making.

Clinical Best Practices

  • Employ interpretable machine learning techniques for clinical predictions.
  • Use Shapley additive explanations (SHAP) for understanding predictor contributions.

Related Resources & Content

Original Source(s)

Interpretable machine learning prediction of live birth after freeze-all FET cycles across transfer-order subgroups

  • by Yu Zhao, He Wang, Lin Wang, Lei Yan, Jiao Liu, Mengyi Teng, Hao Wang, Ting Liu

  • July 17, 2026

Related Content

Age-stratified diagnostic performance of the ovarian-adnexal reporting and data system for adnexal masses: a focus on school-age children, early, and middle adolescents

Association between educational level and acceptance of antenatal respiratory syncytial virus vaccination among Saudi women: a cross-sectional study

Breastfeeding May Help Infants Achieve Adequate Sleep

A nationwide birth cohort found lower odds of short sleep at 1 year among infants breastfed during the first 6 months of life, regardless of formula supplementation.